Kaiming

class deeplay.initializers.kaiming.Kaiming(targets: ~typing.Tuple[~typing.Type[~torch.nn.modules.module.Module], ...] = (<class 'torch.nn.modules.linear.Linear'>, <class 'torch.nn.modules.conv.Conv1d'>, <class 'torch.nn.modules.conv.Conv2d'>, <class 'torch.nn.modules.conv.Conv3d'>, <class 'torch.nn.modules.conv.ConvTranspose1d'>, <class 'torch.nn.modules.conv.ConvTranspose2d'>, <class 'torch.nn.modules.conv.ConvTranspose3d'>, <class 'torch.nn.modules.batchnorm.BatchNorm1d'>, <class 'torch.nn.modules.batchnorm.BatchNorm2d'>, <class 'torch.nn.modules.batchnorm.BatchNorm3d'>), mode: str = 'fan_out', nonlinearity: str = 'relu', fill_bias: bool = True, bias: float = 0.0)

Bases: Initializer

Methods Summary

initialize_tensor(tensor, name)

Methods Documentation

initialize_tensor(tensor, name)